Blok AWV HC2: RCT

HC2: RCT

ReDuCe

ReDuCe is a new diuretic drug for patients with hypertension. Its effect has to be studied → a research question has to be made:

  • What is the effect of a new diuretic drug (ReDuCe) versus no diuretic treatment on blood pressure in patients who have an increased blood pressure?
    • Classification: treatment research
    • Patients: subjects with an increased blood pressure
    • Intervention: 40 mg ReDuCe
    • Comparator: no diuretic treatment
    • Outcome: blood pressure reduction

Effect

After 6 weeks of treatment, a patient prescribed with ReDuCe has a normalized blood pressure → the effect. However, this effect can have several causes:

  • Start of the pharmacological therapy (ReDuCe)
  • Stopping of smoking
  • Starting to go to the gym
  • More adherence to β-blocker treatment
  • Fear of the doctor the first time the blood pressure was measured
    • This is called “white coat hypertension”
  • Use of a more precise measurement instrument the second time
  • The blood pressure fluctuation over time
    • Regression to the mean has to be applied
    • Sometimes the blood pressure is relatively high, sometimes relatively low
  • Et cetera

Outcome

The outcome is a combination of 4 phenomena:

  • Treatment (T)
  • Natural course (NC)
    • Natural reasons for why the blood pressure goes up or down
  • Extraneous factors (EF)
    • E.g. going to the gym
  • Error processes (V)
    • Variation of the measurement device

Therefore, outcome = T + NC + EF + V. The interest mainly lies in the effect of the treatment (T):

  • Outcome with treatment : T + NC + EF + V
  • Outcome without treatment : NC + EF + V

Comparison:

To identify the effect of treatment, 2 (or more) groups need to be compared. These groups should be comparable with respect to NC, EF and V, and differ only with respect to treatment. In this case, an observed difference in the outcome between the groups can be attributed to the only aspects that the 2 groups differ on → the treatment. Comparability is necessary.

Design elements

A randomized controlled trial is the number 1 design to achieve comparability. In order to achieve comparability, an RCT typically has 3 design elements:

  • Randomization
    • Concealment of treatment allocation → treatment allocation independent of patient characteristics
      • A remote algorithm that is concealed for both the patient and physician
        • The physician who asked patients to participate does not know what treatment the next patient will receive, nor do the patients themselves
      • The physician can cheat on other processes
  • Blinding
    • Participants should not now which treatment they receive → can influence their behavior
      • This also applies to the treating physicians, nurses and relatives
      • Aims to keep the groups comparable during the follow-up
    • Methods
      • Placebo
        • Tastes/looks/smells like the active treatment, but does not contain the active compound
        • Sometimes difficult in case of surgery or physiotherapy
      • Active comparator
        • E.g. ReDuCe (40 mg) versus hydrochlorothiazide (25 mg)
    • Outcome assessment: the one who measures the outcome shouldn’t know about treatment status because that could influence the measurement
      • E.g. blood pressure, quality of life, etc.
      • Exception: all-cause mortality
  • Standardization
    • 3 elements need to be standardized
      • Standardization of intervention
        • Administration, frequencies and dosages
      • Standardization of concomitant care
        • What physicians should/should not combine with the treatment
      • Standardization of outcome assessment
        • How the blood pressure should be recorded
    • Aims
      • Minimizing error processes
      • Improving interpretability of treatment effects

In short, several elements are necessary to achieve comparability in 3 stages of treatment:

  • Start of treatment → randomization and concealment of allocation
  • Follow-up → blinding of the patient and physician
  • Outcome assessment → blinding of the outcome assessor

Research questions

Several things can be done to find the answer to the question: “What is the effect of a new diuretic drug (ReDuCe) versus no diuretic treatment on blood pressure in patients who have an increased blood pressure?”. The intervention is ReDuCe, with either a placebo of hydrochlorothiazide as comparators:

  • Intervention
    • Patients: subjects with an increased blood pressure
    • Intervention: 40 mg ReDuCe
    • Comparator: no diuretic treatment
    • Outcome: blood pressure after 6 weeks of treatment
  • Comparator
    • Placebo
      • Patients: subjects with increased blood pressure
      • Intervention: 40 mg of ReDuCe
      • Comparator: placebo
      • Outcome: blood pressure after 6 weeks of treatment
    • Hydrochlorothiazide
      • Patients: subjects with increased blood pressure
      • Intervention: 40 mg of ReDuCe
      • Comparator: 25 mg of hydrochlorothiazide
      • Outcome: blood pressure after 6 weeks of treatment

Equipoise:

It may not be ethical to compare a new drug with a placebo, especially if it is known that the drug is effective and available → comparison with an effective comparator is necessary. Some comparisons may also not be relevant. Clinical equipoise provides the ethical basis for medical research that involves assigning patients to different treatment arms of a clinical trial.

Primary endpoint, analysis and measure

Primary endpoint:

The primary/clinical endpoint of a clinical trial is the endpoint for which the trial is powered. It is the main result that is measured at the end of a study to see if a given treatment worked.Secondary endpoints are additional endpoints for which the trial may not be powered.

Primary analysis:

The primary analysis is the intention to treat. It is the original analysis of data collected for a research study. In an intention to treat analysis, anyone randomized into one of the study groups must be included in the final analysis in the group to which they were originally randomized, regardless of whether they adhered to the protocol or not.

Primary measure:

The primary outcome measure is the outcome that an investigator considers to be the most important among the many outcomes that are to be examined in the study. The primary outcome needs to be defined at the time the study is designed.

Randomization

Block randomization:

Block randomization is done by the computer and ensures that the disbalance of total numbers in a type of treatment can never be substantial. This is called random permuted blocks (RPBs):

  • Sequences can never be more than 2 out of balance
  • If there are 4 groups, trials need to consist of 4, 8, 12, etc. patients
    • Are predictable to a certain extent → to prevent this, block length variation is applied (both length 6 blocks and length 4 blocks are used)

Voice response system:

Voice response systems are used to conduct clinical trials and manage the large volumes of data generated. The caller responds to questions, which will be logged into a database and possibly recorded at the same time to confirm authenticity. Applications include patient randomization and drug supply management. They are also used in recording patient diaries and questionnaires. This allows callers to obtain data relatively anonymously, which allows callers to receive anonymous access to test results. The voice response system is used to preserve privacy and avoid potential embarrassment of sensitive information or test results.

Declaration of Helsinki

The declaration of Helsinki provides guidance to physicians engaged in clinical research and focuses on the responsibilities of researchers for the protection of research subjects → in medical research involving human subjects capable of giving informed consent, each potential subject must be adequately informed of the aims, methods, sources of funding, any possible conflicts of interest, institutional affiliations of the researcher, the anticipated benefits and potential risks of the study.

Preregistration

Preregistration separates hypothesis-generating (exploratory) from hypothesis-testing (confirmatory) research. Both are important. But the same data cannot be used to generate and test a hypothesis, which can happen unintentionally and reduce the credibility of your results. Addressing this problem through planning improves the quality and transparency of your research. This helps you clearly report your study and helps others who may wish to build on it.

Check page access:
Public
Check more or recent content:

Blok AWV2 2020/2021 UL

Blok AWV HC1: Research questions

Blok AWV HC1: Research questions

HC1: Research questions

Medical research

The ultimate goal of medical research is to improve medical practice. There are different aspects of medical practice which form 4 classes of medical research:

  • Etiology (prevention/risk factors of a medical disease)
    • Is a high caloric diet a risk factor for cardiovascular disease?
  • Diagnosis
    • What is the probability of having a hip fracture if the affected leg is shorter and in exorotation?
  • Treatment
    • Does chloroquine treatment reduce the risk of mortality among COVID-19 patients admitted to the ICU?
  • Prognosis
    • What is the probability of dying within 5 years after breast cancer diagnosis?

Research questions

Research questions arise in practice. It is important to particularly articulate a research question → they are the starting point when designing a study or when reading a paper. A research question should be answerable and have standard elements/components.

Components:

Research questions can consist of several types of standard components:

  • PICO: most often used
    • Patient (population)
    • Intervention
    • Comparator
    • Outcome
  • DDO
    • Domain
    • Determinant
    • Outcome

Examples:

Examples of research questions are:

  • To what extent does alemtuzumab compared to interferon-β improve the time until relapse occurs in patients with relapsing remitting MS?
    • Classification: treatment
    • Patients: patients with relapsing remitting MS
    • Intervention: alemtuzumab
    • Comparator: interferon-β
    • Outcome: time until relapse occurs
  • What is the predictive value of a second ultrasound, in case a first ultrasound was inconclusive, in patients suspected of having an acute appendicitis?
    • Classification: diagnosis
    • Patients: patients suspected of having an acute appendicitis, in whom a first ultrasound was inconclusive
    • Intervention: second ultrasound
    • Comparator: /
    • Outcome: appendicitis
  • Is smoking a risk factor for lung cancer?
    • Classification: etiology
    • Patients: humans
    • Intervention: smoking
    • Comparator: no smoking
    • Outcome: lung cancer
Access: 
Public
Blok AWV HC2: RCT

Blok AWV HC2: RCT

HC2: RCT

ReDuCe

ReDuCe is a new diuretic drug for patients with hypertension. Its effect has to be studied → a research question has to be made:

  • What is the effect of a new diuretic drug (ReDuCe) versus no diuretic treatment on blood pressure in patients who have an increased blood pressure?
    • Classification: treatment research
    • Patients: subjects with an increased blood pressure
    • Intervention: 40 mg ReDuCe
    • Comparator: no diuretic treatment
    • Outcome: blood pressure reduction

Effect

After 6 weeks of treatment, a patient prescribed with ReDuCe has a normalized blood pressure → the effect. However, this effect can have several causes:

  • Start of the pharmacological therapy (ReDuCe)
  • Stopping of smoking
  • Starting to go to the gym
  • More adherence to β-blocker treatment
  • Fear of the doctor the first time the blood pressure was measured
    • This is called “white coat hypertension”
  • Use of a more precise measurement instrument the second time
  • The blood pressure fluctuation over time
    • Regression to the mean has to be applied
    • Sometimes the blood pressure is relatively high, sometimes relatively low
  • Et cetera

Outcome

The outcome is a combination of 4 phenomena:

  • Treatment (T)
  • Natural course (NC)
    • Natural reasons for why the blood pressure goes up or down
  • Extraneous factors (EF)
    • E.g. going to the gym
  • Error processes (V)
    • Variation of the measurement device

Therefore, outcome = T + NC + EF + V. The interest mainly lies in the effect of the treatment (T):

  • Outcome with treatment : T + NC + EF + V
  • Outcome without treatment : NC + EF + V

Comparison:

To identify the effect of treatment, 2 (or more) groups need to be compared. These groups should be comparable with respect to NC, EF and V, and differ only with respect to treatment. In this case, an observed difference in the outcome between the groups can be attributed to the only aspects that the 2 groups differ on → the treatment. Comparability is necessary.

Design elements

A randomized controlled trial is the number 1 design to achieve comparability. In order to achieve comparability, an RCT typically has 3 design elements:

  • Randomization
    • Concealment of treatment allocation → treatment allocation independent of patient characteristics
      • A remote algorithm that is concealed for both the patient and physician
        • The physician who asked patients to participate does not know what treatment the next patient will receive, nor do the patients themselves
      • The physician can cheat on other processes
  • Blinding
    • Participants should not now which treatment they receive → can influence their behavior
      • This also applies to the treating physicians, nurses and relatives
      • Aims to keep the groups comparable during the follow-up
    • Methods
      • Placebo
        • Tastes/looks/smells like the active treatment, but does not contain the active compound
        • Sometimes difficult in case of surgery or physiotherapy
.....read more
Access: 
Public
Blok AWV HC3: Sample size calculation

Blok AWV HC3: Sample size calculation

HC3: Sample size calculation

Motivation

In medical papers, there often is a statistical analysis paragraph with a motivation of the number of people in a sample of a study.

The aim of an RCT is to compare 2 treatments → patients are recruited to the study and randomized to treatment A or B. It also needs to be determined how many patients are included in the RCT → the sample size:

  • Too few
    • Imprecise results → no power to determine the effect of treatment
  • Too many
    • Takes a lot of time, effort and money
    • It is unethical to include many patients in a study

Factors

Factors for deciding sample size are:

  • Practical
    • Number of eligible patients treated at the center
    • Number of patients willing to participate
    • Time
    • Money
  • Statistical
    • How big of an effect can be detected with a given number of patients?

Hypothesis testing

Hypothesis testing yields P-values and statements of statistic significance. Hypothesis testing is done as follows:

  1. Decide on a null hypothesis (H0) about the population
    • H0: there is no difference between the 2 groups
  2. Take a representative sample of the population
  3. Calculate the observed difference in the sample
  4. Calculate the p-value
    • P-value: the probability to observe at least this difference if H0is true
      • This is done by a statistical test
  5. If the p-value is smaller than the prespecified value α, H0is rejected
    • The value αis called the significance level

Mistakes:

However, mistakes can be made in hypothesis testing. H0is rejected in case the observations are unlikely to occur if H0is true, and not if they are impossible:

  • Correct decisions
    • H0is not rejected + H0 is true
    • H0is rejected + H0is not true
  • Incorrect decisions
    • H0is rejected + H0is true → a type 1 error
      • α = the probability of a type 1 error
    • H0is not rejected + H0is not true → a type 2 error
      • β = the probability of a type 2 error
        • Power = 1 - β

Power:

The power is the probability of finding a significant effect in a sample when the effect is really present in the population. This depends on:

  • Relevant difference (effect size)
  • Sample size
    • If the sample size decreases, the power will also decrease
  • Variance/standard deviation
    • If there is more variation in a group the power will be smaller
  • Significance level α

The aim is to have a study with a large power of 80-90%.

Example:

There is an RCT on patients with high blood pressure:

  • Intervention: 40 mg of ReDuCe
  • Comparator: 25 mg of hydrochlorothiazide
  • Outcome: blood pressure after 6 weeks of treatment

In order to calculate the optimal sample size of this trial, some extra information is necessary:

    .....read more
    Access: 
    Public
    Blok AWV HC4: Cohort studies

    Blok AWV HC4: Cohort studies

    HC4: Cohort studies

    Study designs

    Medical research almost always requires collection of data. Study design described how is the study set up and how the data are collected. There are 2 types of study design:

    • Cohort study
    • Case-control study

    Cohort

    A cohort is a group of people with a common characteristic (gender, diabetes, age, etc.). A cohort study follows such a group over time and records certain outcomes in a follow-up study or longitudinal study. Usually, 2 or more groups are compared. For instance, with patients who are hospitalized for Covid-19, there is a follow-up, record of the mortality and comparison of chloroquine treatment versus no chloroquine treatment.

    Example:

    Cohort studies are often simplified in tables. An example is the association between smoking and lung cancer:

    • Cases: individuals who develop of an outcome of interest
    • N = size of the group
    • T = person time
      • If a person contributes 50 weeks to the study, and another person 2 weeks, the person time is 52 weeks → 1 person year

     

    Cases

    N

    Exposed

    A

    N1

    Unexposed

    B

    N0

     

    Cases

    N

    Smokers

    1600

    100 000

    Unexposed

    400

    200 000

     

     

    Cases

    T

    Exposed

    A

    T1

    Unexposed

    B

    T0

     

    Cases

    N

    Exposed

    1600

    300 000

    Unexposed

    400

    600 000

    With a cohort, the risk/rate can be estimated:

    • Cumulative incidence = A/N1→ 1600/100 000 = 1,6%
      • The cumulative is also known as the risk → the risk of smokers getting lung cancer is 1,6%
      • Time is not taken into account
    • Incidence rate = (A/T1) = 1600/300 000 years = 5,3 per 1000 person years
      • Time is taken into account
      • It is expected that 5,3 per 1000 individuals develops lung cancer in 1 year
    • Risk ratio (RR) = (A/N1)/(B/N0) → (1600/100 000)/(400/200 000) = 1,6%/0,2% = 8
      • Can be either the cumulative incidence ratio or the incidence rate ratio
        • Cumulative incidence risk ratio = (A/N1)/(B/N0)
        • Incidence rate ratio = (A/T1)/(B/T0)
      • The risk of developing lung cancer is 8x as large for smokers compared to non-smokers

    Cohort versus dynamic population

    There are several differences between a cohort and a dynamic population:

    • Cohort
      • Membership is established during a certain period in time, defined
    .....read more
    Access: 
    JoHo members
    Blok AWV HC5: Case control studies

    Blok AWV HC5: Case control studies

    HC5: Case control studies

    Case-control study

    In a case control study, instead of a census (information about everybody), sampling is done. The cases are compared to a sample of the entire population. This happens as follows:

    1. Case detection
    2. Sample of the controls
    3. Exposure status assessment among cases and among controls
      • E.g. comparison between the smoking status among the population and the smoking status among the population
    4. Exposure-outcome relation estimation

    Case-control versus cohort:

    A case-control study is very efficient compared to a cohort study:

    • Cohort: requires information about the entire study population
    • Case-control: requires information about part of the controls
      • Advantage: practical efficiency, particularly when:
        • Disease is rare
        • There is a long/unknown latency period
        • Assessment exposure is expensive
      • Disadvantage: it is not possible to estimate absolute disease frequencies (risk/rate)

    Case-control studies do not allow for:

    • Randomization
    • Absolute measures of disease frequency

    Odds ratio

    The odds ratio is the ratio of odds of exposure among cases and odds of exposure among controls. It is the only measure that can be estimated with a case control study.

    Case-control

    Cases

    Controls

    Exposed

    a

    c

    Unexposed

    b

    d

    The following calculations can be done:

    • Odds ratio (OR) = (a/b)/(c/d) = ad/bc

    Interpretation:

    The interpretation of the odds ratio depends on how the control study is done and what the controls represent. How this can be interpreted depends on the moment of sampling controls. Moments of sampling controls are:

    • At the end of the follow-up → sampling from non-cases
    • At the start of the follow-up → case-cohort
    • During the follow-up (each time a case occurs) → incidence density sampling
      • Each time a case is identified, a control is sampled from the cohort

    Controls can represent various things, such as:

    • Non-cases
    • Total number of subjects
    • Person time

    Sampling of non-cases:

    Case-control

    Cases

    Non-cases

    N

    Person time

    Exposed

    A

    C

    N1(A+C)

    T1

    Unexposed

    B

    D

    N0(B+D)

    T0

    In this case, non-cases (those who did not develop the outcome of interest) are sampled → the controls represent the non-cases in the cohort study:

    • c = k x C
    • d = k x D
      • OR = ad/bc = (a/(k x C))/(b/(k x D))
      • RR = (A/(A+C))/(B/(B+D)) = (A/C)/(B/D) = AD/BC = OR
        • This only is the case if A ≪C and B ≪D → in case of a rare outcome
          • If the outcome is <10%
          • The odds ratio can be interpreted as the risk ratio
    .....read more
    Access: 
    JoHo members
    Blok AWV HC6+7: Bias

    Blok AWV HC6+7: Bias

    HC6+7: Bias

    Medical research

    Medical research often consists of the quantification of a phenomenon, for example quantifying the effect of cholesterol lowering treatment on the risk of cardiovascular events among those with elevated serum cholesterol levels. Ideally, results apply not only to those who participate in the study (the study population/sample), but also to others with elevated cholesterol levels (the domain).

    The domain consists of a large group for whom the results of the study should apply. Of this domain, a sample is selected based on:

    • In-/exclusion criteria
    • Region
    • Time period
    • Et cetera

    While the study is done within this sample, the results of the study should apply to the domain. If there is a systematic error, results of the study do not apply to the domain.

    Systematic errors:

    Systematic errors in design, conduct or analysis may lead to erroneous results → bias. An example of a systematic error is a broken measuring tape when measuring the length of something. Each time the measuring tape is used, results are incorrect → a systematic error is not solved by a large sample size.

    Random errors:

    Random errors can be decreased by increasing the sample size. As the study size increases, random errors start playing a increasingly smaller role.

    Sources of bias

    There are 3 sources of bias:

    • Measurement errors → information bias
    • Missing data → selection bias
    • Incomparability of study groups → confounding

    There can be bias in different parts of studies, depending on the study type:

    • Randomized trial
      • Outcome
    • Cohort study
      • Exposure
      • Outcome
      • Confounders
    • Case-control study
      • Exposure
      • Outcome
      • Confounders

    Measurement errors

    Examples of measurement errors are:

    • Questionnaires for measuring body weight instead of scales
    • Drug use measured by “prescription information” instead of controlling if the drugs actually are taken
    • Measuring smoking status with “yes/no” instead of pack years

    This changes the risk ratio → results of the study are (often) incorrect.

    Consequences:

    Measurement errors can have different consequences:

    • Can result in over-/underestimation
    • Better to prevent than to cure
    • Correction is possible

    Missing data

    In case of missing data, certain information is not available:

    • Questionnaire is not returned
    • Question is not answered
    • Study drop-outs
    • Individuals not willing to participate

    The extent of the impact of missing data often depends on the research question, study design, data collection, etc. This changes the risk ratio → a small percentage of missing data (3%) can lead to 100% bias, but this doesn’t necessarily happen → 50% missing data can also result in no bias (the ratio remains the same). Depending on if it is a selective or random process, missing data has a different influence on the results.

    Selection bias:

    Selection bias arises when in either of the exposure groups, a selection was made on stroke. Selecting on the outcome in a follow-up study hardly ever occurs since the participants have not yet developed the outcome at the start of follow-up.

    Meta-analysis:

    .....read more
    Access: 
    JoHo members
    Blok AWV HC8+9: Survival analysis

    Blok AWV HC8+9: Survival analysis

    HC8+9: Survival analysis

    When to use survival analysis

    Survival is used to determine when a certain event happens, such as:

    • When a tumor develops after exposure to a carcinogen
    • When a patient dies after a cancer diagnosis
    • When a patient becomes pregnant after the start of fertility treatment
    • When a graft is rejected after transplantation

    Possible questions that can be answered with survival analysis are:

    • What is the distribution of the survival times?
    • Is there a difference in expected life-time between different treatments?
    • What is the fastest way to become pregnant?
    • Which factors predict 5-year survival probabilities?

    Example:

    For patients with end stage renal disease, it needs to be determined which treatment gives better survival:

    • Hemodialysis (HD)
    • Peritoneal dialysis (PD)

    Survival probabilities and survival times after start of dialysis can possibly be compared with help of T-tests of Chi square tests. However, there are several problems:

    • Not all patients died
    • Not all patients have the same follow-up time
      • Some started dialysis a while ago, some started dialysis recently
    • Patients get lost (e.g. migration)

    Censoring

    Because the time of death of all patients isn’t known, some patients have censored survival times. In an ideal world, patients that are still alive in each group are compared after a certain time period. However, some patients may be lost to follow-up. This can be solved by censoring survival times → the time of event (e.g. death) is not observed, it is only known when the patient was last seen alive. Reasons for censoring are:

    • Administrative censoring: individuals do not have the event (death) before the end of the study
    • Lost to follow-up: the patient moves or does not show up for appointments
    • The patient dies of another disease

    Example:

    In the peritoneal dialysis group, 207 patients died and 446 are still alive and were last seen between 0,8 and 5 years after the start of dialysis → the follow-up varies. Not only the data of the 207 patients should be used because it is very informative that someone is still alive after 5 years → all patients must be used.

    This can be shown in a graph with on the y-axis the a line for each patient, with the length of the line corresponding to the time after start of dialysis on the x-axis. Red dots indicate that the patient has died, green dots indicate that the patient is still alive or, if the dots are before the time of measurement, that the patient was lost to follow-up.

    The survival function

    The aim of survival analysis is to estimate the survival function S(t):

    • S(t) = probability that an event occurs after time (t) → the probability to be “alive” at time (t)
    • Always starts at 1 → everyone is alive at the start of study

    Kaplan-Meier method:

    Survival probabilities can be estimated with the Kaplan-Meier method. Information of each patient is used until death/censoring, for instance the information

    .....read more
    Access: 
    JoHo members
    Blok AWV HC10+11: Regression analysis

    Blok AWV HC10+11: Regression analysis

    HC10+11: Regression analysis

    Mean and standard deviation

    Statistics consists of making statements about a population based on data observed from a sample. This is often done using means and standard deviations (σ). The bigger the standard deviation, the bigger the spread in the population.

    For example, the lung function (FEV1 in L) of 40 children is measured:

    • Mean FEV1 = 3,16 L
    • σ = 0,41 L

    This means that roughly 95% of the population has a FEV1 between 3,16 – 0,82 and 3,19 + 0,82 L → approximately 95% of observations are less than 2σ from the mean:

    • 95% CI = (2,34 L, 3,84 L)

    However, lung function depends on many factors such as age and gender. These factors also need to be taken into account.

    Linear regression

    Simple linear regression is regression for continuous outcomes. Linear regression tries to predict or explain a variable → the outcome or the dependent variable (x). This variable is explained by another variable → the explanatory variable (y). A regression line is based on a scatter plot and calculates the mean value of “y” for a value of “x”:

    • y = the dependent variable, outcome and response variable
    • x = the independent variable, covariate, risk factor, predictor and explanatory variable
    • Mean y = β0+ β1x
      • β0= the intercept (“constante”)
        • The predicted value of “y” if “x” is equal to 0
          • Not always clinically meaningful
      • β1= the slope (“richtingscoëfficiënt”)
        • The expected change in the outcome by increasing the exposure of 1 unit if β1 is positive
          • Or decrease, in case β1is negative

    For instance, a regression line can describe the mean FEV1 as function of age:

    • Mean FEV1 = 2,281 + 0,119 x age

    This means that for 2 children with an age difference of 1 year, the expected mean difference in the FEV1 is 0,119 L.

    Error/residual:

    Observations of (x1, y1), (x2, y2), …, (xn, yn) show that each pair represents the values of 1 person. Sometimes, the error can also be taken into account:

    • y = β0+ β1x + e

    The deviations of the regression line are called residuals, which are taken into the error. The error/residual is assumed to be normally distributed with the standard deviation σ. σ indicates how much the observations vary around the regression line:

    • Small σ: all observations are close to the regression line
    • Large σ: some observations are far from the regression line

    The residual is the distance from a single observation to the regression line → the difference between what is observed and what is predicted:

    • yi– (β0+ β1xi)

    Least squares method:

    The unknown true regression line in the population is line y = β0+ β1x. Using the least squares method, the regression line can be estimated by y = b0+ b1x. The b0and b1which minimize the sum of squared residuals need to be selected:

    .....read more
    Access: 
    JoHo members
    Blok AWV HC12: Diagnostische begrippen

    Blok AWV HC12: Diagnostische begrippen

    HC12: Diagnostische begrippen

    Begrippen

    Een kans is een getal tussen 0 en 100% dat weergeeft hoe waarschijnlijk iets is. Deze kans stijgt als een test positief is, en daalt als een test negatief is. Belangrijke termen zijn:

    • Voorafkans/a-priori kans/prevalentie: voor een test
    • Achterafkans/a-posteriori kans/voorspellende waarde: na een test
    • Sensitiviteit: kans op een positieve test als de ziekte aanwezig is
    • Specificiteit: kans op een negatieve test als de ziekte afwezig is
    • Positief voorspellende waarde: kans dat de ziekte aanwezig is als de test positief is
    • Negatief voorspellende waarde: kans dat de ziekte afwezig is als de test negatief is

    Achterafkans

    Op een polikliniek chirurgie komt een jonge patiënt, die sinds een halve dag buikpijn heeft. De pijn is heftig, continue en gelokaliseerd op het punt van McBurney. De dokter denkt aan appendicitis acuta:

    • 20% van alle acute buik patiënten heeft een appendicitis acuta → de voorafkans is 20%
    • Van alle acute buik patiënten met appendicitis acuta zegt 90% pijn te hebben op McBurney → de sensitiviteit is 90%
    • Van alle acute buik patiënten zonder appendicitis acuta zegt 15% pijn te hebben op McBurney → de specificiteit is 85%

    Positieve testuitslagen kunnen terecht positief (TP) of fout positief (FP) zijn:

    • TP = voorafkans op ziekte x sensitiviteit → 20% x 90% = 18%
    • FP = voorafkans op geen ziekte x (1 – specificiteit) → 80% x 15% = 12%

    2x2 tabel:

    Deze gegevens kunnen gezet worden in een 2x2 tabel:

     

    Appendicitis

    Geen appendicitis

    Totaal

    Wel pijn MB

    18%

    12%

    30%

    Geen pijn MB

    2% (0,1 x 0,2)

    68% (0,85 x 0,8)

    70%

    Totaal

    20%

    80%

    100%

    De achterafkans na een positieve test is 18% van 30% → 60% kans. De kans dat de patiënt appendicitis heeft is 60%. Dit heeft ook wel de positief voorspellende waarde:

    • VW+ = TP/(TP + FP) = 18%(18% + 12%) = 60%

    De negatief voorspellende waarde is de kans dat ziekte afwezig is, gegeven de negatieve testuitslag:

    • VW - = TN/(TN + FN) = 68%/(68% + 2%) = 97%
      • Er zijn heel weinig fout negatieve testuitslagen

    Bayes’ theorema

    Thomas Bayes (1701-1761) was een Engelse dominee en wiskundige. Hij is bekend geworden door zijn theorema over conditionele kansen:

    • Als bekend is dat X waar is, wat is dan de kans op Y?
    • Als het vandaag regent, wat is dan de kans dat het morgen regent?
    • Als de test positief is, wat is dan de kans op ziekte?

    Odds:

    Een kans kan beschreven worden als “odds”:

    • Een kans van 50% is een odds van 1:1 → odds van 1
    • Een kans van 80% is een odds van 80:20 → odds van 4
    • Een kans van 20%
    .....read more
    Access: 
    Public
    Blok AWV HC13: Beslisbomen

    Blok AWV HC13: Beslisbomen

    HC13: Beslisbomen

    3 deuren probleem

    Een beslisboom bestaat uit takken met beslisknopen en eindknopen. Een voorbeeld is het drie deuren probleem, waarbij achter 1 deur een auto staat. Vervolgens wordt van 1 deur bekend wordt dat deze fout is waardoor de kans 50% is dat achter 1 van de overgebleven deuren het goede zit. Vervolgens kan de persoon die voor 1 van de overgebleven 2 deuren staat besluiten om wel of niet te wisselen. Voor beide opties zijn 2 mogelijkheden:

    • Niet wisselen
      • Eerst goede deur → kans van 1/3 → de auto wordt gewonnen
      • Eerst foute deur → kans van 2/3 → niks wordt gewonnen
    • Wel wisselen
      • Eerst goede deur → kans van 1/3 → niks wordt gewonnen
      • Eerst foute deur → kans van 2/3 → de auto wordt gewonnen

    Dit zijn de kansen vóór het wisselen. Deze analyse laat zien dat in het geval dat er niet gewisseld wordt, de kans op het winnen van de auto 1/3 is, terwijl als er wel gewisseld wordt, de kans 2/3 is.

    Spijt:

    Spijt ontstaat als de persoon eerst goed stond, en daarna wisselde waardoor de auto alsnog niet is gewonnen.

    Opmerkingen:

    Een aantal opmerkingen bij het 3-deuren probleem zijn:

    • De goede beslissing geeft niet steeds de beste uitkomst
      • Proces- versus uitkomstkwaliteit
      • Effectiviteit versus bijwerkingen
    • Het beslissingscriterium bepaalt de optimale beslissing
      • Wat is het doel?
        • Vooral de auto willen hebben of geen spijt willen hebben?
      • Geanticipeerde spijt → achteraf geen spijt willen hebben

    Beslisbomen

    Met beslisbomen kunnen problemen geanalyseerd worden:

    • Structuur
      • Keuzeknopen, kansknopen en eindknopen
      • Van links naar rechts
    • Getallen
      • Getallen bij de kansknopen
      • De kans op een hele “tak” is p1x p2x …
      • Uitkomsten staan bij de eindknopen
    • Analyseren en optimaliseren
      • Bereken de verwachtingswaarde voor elke beslissing
      • Kies d ebeste verwachte waarde

    Verwachtingswaarde:

    Over het algemeen is de verwachtingswaarde ongeveer “het midden” → in een continue of normale verdeling is de verwachtingswaarde de mediaan. Echter is de uitkomst bij beslisbomen niet continu → er zijn meerdere mogelijkheden. Zo zijn er bij het gooien van een dobbelsteen 6 mogelijkheden, die allemaal een kans van 1/6 hebben. De verwachtingswaarde van een dobbelsteenworp is daarom:

    • 1/6 x 1 + 1/6 x 2 + 1/6 x 3 + 1/6 x 4 + 1/6 x 5 + 1/6 x 6 = 3,5

    De verwachtingswaarde is niet hetzelfde als het gemiddelde → de verwachtingswaarde is een begrip uit de kansrekening en het gemiddelde is een begrip uit de statistiek:

    • Kansrekening
      • Ontstaan in de 16e eeuw, vanwege analyse van kansspelen
      • Het vooraf modelleren en doorrekenen van toeval
        • Bijv. het maken van een model met de dobbelsteen waarmee doorgerekend wordt
    • Statistiek
      • Ontstaan in de 17e eeuw, vanwege (levens)verzekeringen
      • Het achteraf beschrijven en analyseren van data
        • Bijv. het gemiddelde als er 8x is gegooid met een dobbelsteen
    .....read more
    Access: 
    Public
    Blok AWV HC14: Test en behandeldrempel

    Blok AWV HC14: Test en behandeldrempel

    HC14: Test en behandeldrempel

    Behandeldrempel

    De behandeldrempel beantwoord de klinische vraag: “Hoe zeker moet ik zijn van de ziekte, voordat ik overga tot behandeling, wetende dat elke behandeling zowel voor- als nadelen heeft?”

    Kosten en baten:

    Elke behandeling heeft voor- en nadelen. De consequenties van een behandeling bepalen wanneer een behandeling wordt ingezet → er wordt gekeken naar de balans tussen de voor- en nadelen:

    • Baat: vermindering van de schade door de ziekte
      • Kan alleen optreden bij de aanwezigheid van die ziekte
    • Kosten: gezondheidsschade door de behandeling zelf
      • Bij mensen met en zonder de ziekte
        • Bij mensen met de ziekte, zitten de kosten al verwerkt in de baat
        • Mensen zonder de ziekte hebben alleen de kosten
      • Baat het niet, dat schaadt het niet

    Het volgende geldt:

    • Bij zekerheid over de ziekte
      • Bij mensen met de ziekte is er baat
      • Bij mensen zonder de ziekte zijn er kosten
    • Bij onzekerheid over de ziekte
      • Bij mensen met een hoge kans op de ziekte is er meer baat dan kosten
      • Bij mensen met een lage kans op de ziekte zijn er meer kosten dan baat

    Bij de behandeldrempel is de baat gelijk aan de kosten.

    Beslisboom:

    De baat en kosten zijn ook zichtbaar in de beslisboom, bijvoorbeeld over AAAA:

    • Opereren
      • De patiënt heeft AAAA → overlevingskans van 40%
        • De kans hierop is pAAAA
      • De patiënt heeft iets anders → overlevingskans van 95%
    • Afwachten
      • De patiënt heeft AAAA → overlevingskans van 0%
        • De kans hierop is pAAAA
      • De patiënt heeft iets anders → overlevingskans van 100%

    In dit geval is de baat 40% - 0% = 40%, en zijn de kosten 100% - 95% = 5%.

    Utility:

    Elke beslissing heeft zijn eigen uitkomst → elke uitkomst heeft een “utility” (waarde of nut):

    • UTP= nut van “true positive” → terecht behandeld
    • UFP= nut van “false positive” → onterecht behandeld
    • UFN= nut van “false negative” → onterecht onbehandeld
    • UTN= nut van “true negative” → terecht onbehandeld

    Hiermee kunnen de baten en kosten berekend worden:

    • Benefit (B) = UTP– UFN
      • Het verschil tussen wel en niet behandelen bij mensen met de ziekte, inclusief de behandelschade
    • Costs (C) = UTN– UFP
      • Het verschil tussen wel en niet behandelen bij mensen zonder de ziekte, exclusief het behandelvoordeel

    De “expected utility” (EU) is de verwachtingswaarde van het nut van de 2 mogelijke strategieën:

    • EU (wel behandelen) = p x UTP+ (1-p) x UFP
    • EU (niet behandelen) = p x UFN+ (1-p) x UTN

    Door EU (wel behandelen) gelijk te stellen aan EU (niet behandelen), kan berekend worden wanneer het even goed is om wel/niet te behandelen:

    1. EU (wel behandelen) = EU (niet behandelen)
    2. p x UTP+ (1-p) x UFP= p x UFN+ (1-p) x UTN
    3. p x (UTP– UFN) = (1-p) x (UTN–
    .....read more
    Access: 
    Public
    Work for WorldSupporter

    Image

    JoHo can really use your help!  Check out the various student jobs here that match your studies, improve your competencies, strengthen your CV and contribute to a more tolerant world

    Working for JoHo as a student in Leyden

    Parttime werken voor JoHo

    Check more of this topic?
    How to use more summaries?


    Online access to all summaries, study notes en practice exams

    Using and finding summaries, study notes en practice exams on JoHo WorldSupporter

    There are several ways to navigate the large amount of summaries, study notes en practice exams on JoHo WorldSupporter.

    1. Starting Pages: for some fields of study and some university curricula editors have created (start) magazines where customised selections of summaries are put together to smoothen navigation. When you have found a magazine of your likings, add that page to your favorites so you can easily go to that starting point directly from your profile during future visits. Below you will find some start magazines per field of study
    2. Use the menu above every page to go to one of the main starting pages
    3. Tags & Taxonomy: gives you insight in the amount of summaries that are tagged by authors on specific subjects. This type of navigation can help find summaries that you could have missed when just using the search tools. Tags are organised per field of study and per study institution. Note: not all content is tagged thoroughly, so when this approach doesn't give the results you were looking for, please check the search tool as back up
    4. Follow authors or (study) organizations: by following individual users, authors and your study organizations you are likely to discover more relevant study materials.
    5. Search tool : 'quick & dirty'- not very elegant but the fastest way to find a specific summary of a book or study assistance with a specific course or subject. The search tool is also available at the bottom of most pages

    Do you want to share your summaries with JoHo WorldSupporter and its visitors?

    Quicklinks to fields of study (main tags and taxonomy terms)

    Field of study

    Access level of this page
    • Public
    • WorldSupporters only
    • JoHo members
    • Private
    Statistics
    1283
    Comments, Compliments & Kudos:

    Add new contribution

    CAPTCHA
    This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.
    Image CAPTCHA
    Enter the characters shown in the image.
    Promotions
    Image
    The JoHo Insurances Foundation is specialized in insurances for travel, work, study, volunteer, internships an long stay abroad
    Check the options on joho.org (international insurances) or go direct to JoHo's https://www.expatinsurances.org